Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023 (2404.01082v2)

Published 1 Apr 2024 in eess.IV

Abstract: Cardiac MRI, crucial for evaluating heart structure and function, faces limitations like slow imaging and motion artifacts. Undersampling reconstruction, especially data-driven algorithms, has emerged as a promising solution to accelerate scans and enhance imaging performance using highly under-sampled data. Nevertheless, the scarcity of publicly available cardiac k-space datasets and evaluation platform hinder the development of data-driven reconstruction algorithms. To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th International Conference on MICCAI. CMRxRecon presented an extensive k-space dataset comprising cine and mapping raw data, accompanied by detailed annotations of cardiac anatomical structures. With overwhelming participation, the challenge attracted more than 285 teams and over 600 participants. Among them, 22 teams successfully submitted Docker containers for the testing phase, with 7 teams submitted for both cine and mapping tasks. All teams use deep learning based approaches, indicating that deep learning has predominately become a promising solution for the problem. The first-place winner of both tasks utilizes the E2E-VarNet architecture as backbones. In contrast, U-Net is still the most popular backbone for both multi-coil and single-coil reconstructions. This paper provides a comprehensive overview of the challenge design, presents a summary of the submitted results, reviews the employed methods, and offers an in-depth discussion that aims to inspire future advancements in cardiac MRI reconstruction models. The summary emphasizes the effective strategies observed in Cardiac MRI reconstruction, including backbone architecture, loss function, pre-processing techniques, physical modeling, and model complexity, thereby providing valuable insights for further developments in this field.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (99)
  1. Modl: Model-based deep learning architecture for inverse problems. IEEE transactions on medical imaging 38, 394–405.
  2. Scan-specific robust artificial-neural-networks for k-space interpolation (raki) reconstruction: Database-free deep learning for fast imaging. Magnetic resonance in medicine 81, 439–453.
  3. Multi-coil mri reconstruction challenge—assessing brain mri reconstruction models and their generalizability to varying coil configurations. Frontiers in Neuroscience 16. URL: https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.919186, doi:10.3389/fnins.2022.919186.
  4. Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Transactions on medical imaging 37, 2514–2525.
  5. Bicubic++: Slim, slimmer, slimmest-designing an industry-grade super-resolution network, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1623–1632.
  6. Dynamic mri using model-based deep learning and storm priors: Modl-storm. Magnetic resonance in medicine 82, 485–494.
  7. Multi-centre, multi-vendor and multi-disease cardiac segmentation: the m&ms challenge. IEEE Transactions on Medical Imaging 40, 3543–3554.
  8. Ocmr (v1. 0)–open-access multi-coil k-space dataset for cardiovascular magnetic resonance imaging. arXiv preprint arXiv:2008.03410 .
  9. Nafssr: Stereo image super-resolution using nafnet, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 1239–1248.
  10. Score-based diffusion models for accelerated mri. Medical image analysis 80, 102479.
  11. Compressed sensing. IEEE Transactions on information theory 52, 1289–1306.
  12. Vs-net: Variable splitting network for accelerated parallel mri reconstruction, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part IV 22, Springer. pp. 713–722.
  13. Replication Data for: Multi-Domain Convolutional Neural Network (MD-CNN) For Radial Reconstruction of Dynamic Cardiac MRI. URL: https://doi.org/10.7910/DVN/CI3WB6, doi:10.7910/DVN/CI3WB6.
  14. Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: basic concepts and status of clinical development. Frontiers in Cardiovascular Medicine 9, 953823.
  15. Humus-net: Hybrid unrolled multi-scale network architecture for accelerated mri reconstruction. Advances in Neural Information Processing Systems 35, 25306–25319.
  16. U-net: deep learning for cell counting, detection, and morphometry. Nature methods 16, 67–70.
  17. Spatiotemporal implicit neural representation for unsupervised dynamic mri reconstruction. arXiv preprint arXiv:2301.00127 .
  18. Imjense: Scan-specific implicit representation for joint coil sensitivity and image estimation in parallel mri. IEEE Transactions on Medical Imaging .
  19. Application of the alternating direction method of multipliers to separable convex programming problems. Computational Optimization and Applications 1, 93–111.
  20. Generalized autocalibrating partially parallel acquisitions (grappa). Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine 47, 1202–1210.
  21. Adaptive diffusion priors for accelerated mri reconstruction. Medical Image Analysis , 102872.
  22. Accelerated cardiac t1 mapping in four heartbeats with inline myomapnet: a deep learning-based t1 estimation approach. Journal of Cardiovascular Magnetic Resonance 24, 1–15.
  23. Learning a variational network for reconstruction of accelerated mri data. Magnetic resonance in medicine 79, 3055–3071.
  24. Systematic evaluation of iterative deep neural networks for fast parallel mri reconstruction with sensitivity-weighted coil combination. Magnetic Resonance in Medicine 86, 1859–1872.
  25. Real-time cardiovascular mr with spatio-temporal artifact suppression using deep learning–proof of concept in congenital heart disease. Magnetic resonance in medicine 81, 1143–1156.
  26. Denoising diffusion probabilistic models, in: Advances in neural information processing systems, pp. 6840–6851.
  27. Deep low-rank plus sparse network for dynamic mr imaging. Medical Image Analysis 73, 102190.
  28. Neural implicit k-space for binning-free non-cartesian cardiac mr imaging, in: International Conference on Information Processing in Medical Imaging, Springer. pp. 548–560.
  29. Cardiac mr: from theory to practice. Frontiers in cardiovascular medicine 9, 826283.
  30. Cardiac mri t1 and t2 mapping: A new crystal ball?
  31. Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magnetic resonance in medicine 81, 116–128.
  32. Spatio-temporal deep learning-based undersampling artefact reduction for 2d radial cine mri with limited training data. IEEE transactions on medical imaging 39, 703–717.
  33. Autofocusing+: Noise-resilient motion correction in magnetic resonance imaging, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 365–375.
  34. Deep learning methods for automatic evaluation of delayed enhancement-mri. the results of the emidec challenge. Medical Image Analysis 79, 102428.
  35. A simple baseline for video restoration with grouped spatial-temporal shift, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9822–9832.
  36. Atrialjsqnet: A new framework for joint segmentation and quantification of left atrium and scars incorporating spatial and shape information. Medical image analysis 76, 102303.
  37. Universal undersampled mri reconstruction, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VI 24, Springer. pp. 211–221.
  38. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 .
  39. Compressed sensing mri. IEEE signal processing magazine 25, 72–82.
  40. Reconstruction of undersampled radial free-breathing 3d abdominal mri using stacked convolutional auto-encoders. Medical Physics 45, 2023–2032.
  41. Transfer learning enhanced generative adversarial networks for multi-channel mri reconstruction. Computers in Biology and Medicine 134, 104504.
  42. Pic-gan: a parallel imaging coupled generative adversarial network for accelerated multi-channel mri reconstruction. Diagnostics 11, 61.
  43. Parallel imaging with a combination of sensitivity encoding and generative adversarial networks. Quantitative Imaging in Medicine and Surgery 10, 2260.
  44. Which gan? a comparative study of generative adversarial network-based fast mri reconstruction. Philosophical Transactions of the Royal Society A 379, 20200203.
  45. Region-focused multi-view transformer-based generative adversarial network for cardiac cine mri reconstruction. Medical Image Analysis 85, 102760.
  46. Multi-channel gan–based calibration-free diffusion-weighted liver imaging with simultaneous coil sensitivity estimation and reconstruction. Frontiers in Oncology 13, 1095637.
  47. Adaptive feature aggregation based multi-task learning for uncertainty-guided semi-supervised medical image segmentation. Expert Systems with Applications 232, 120836.
  48. Dudocaf: Dual-domain cross-attention fusion with recurrent transformer for fast multi-contrast mr imaging, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 474–484.
  49. Stadnet: Spatial-temporal attention-guided dual-path network for cardiac cine mri super-resolution. Medical Image Analysis , 103142.
  50. Fast and low-gpu-memory abdomen ct organ segmentation: the flare challenge. Medical Image Analysis 82, 102616.
  51. Deep learning segmentation of the right ventricle in cardiac mri: The m&ms challenge. IEEE Journal of Biomedical and Health Informatics .
  52. Reconstruction techniques for cardiac cine mri. Insights into imaging 10, 1–16.
  53. Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG) 41, 1–15.
  54. Generalising deep learning mri reconstruction across different domains. arXiv preprint arXiv:1902.10815 .
  55. Unrolled and rapid motion-compensated reconstruction for cardiac cine mri. Medical Image Analysis 91, 103017.
  56. Right ventricle segmentation from cardiac mri: a collation study. Medical image analysis 19, 187–202.
  57. An open benchmark challenge for motion correction of myocardial perfusion mri. IEEE journal of biomedical and health informatics 21, 1315–1326.
  58. Promptir: Prompting for all-in-one blind image restoration. arXiv preprint arXiv:2306.13090 .
  59. Sense: sensitivity encoding for fast mri. Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine 42, 952–962.
  60. Synergistic multi-contrast cardiac magnetic resonance image reconstruction. Philosophical Transactions of the Royal Society A 379, 20200197.
  61. Complementary time-frequency domain networks for dynamic parallel mr image reconstruction. Magnetic Resonance in Medicine 86, 3274–3291.
  62. Artificial intelligence-based image reconstruction in cardiac magnetic resonance, in: Artificial Intelligence in Cardiothoracic Imaging. Springer, pp. 139–147.
  63. Convolutional recurrent neural networks for dynamic mr image reconstruction. IEEE transactions on medical imaging 38, 280–290.
  64. k-t next: dynamic mr image reconstruction exploiting spatio-temporal correlations, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22, Springer. pp. 505–513.
  65. U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, Springer. pp. 234–241.
  66. Mednext: Transformer-driven scaling of convnets for medical image segmentation, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 405––415.
  67. A deep cascade of convolutional neural networks for dynamic mr image reconstruction. IEEE transactions on Medical Imaging 37, 491–503.
  68. Exploiting motion for deep learning reconstruction of extremely-undersampled dynamic mri, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 704–712.
  69. Implicit neural representations with periodic activation functions, in: Advances in neural information processing systems, pp. 7462–7473.
  70. An open, multi-vendor, multi-field-strength brain mr dataset and analysis of publicly available skull stripping methods agreement. NeuroImage 170, 482–494.
  71. End-to-end variational networks for accelerated mri reconstruction, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part II 23, Springer. pp. 64–73.
  72. Statistical shape modeling of the left ventricle: myocardial infarct classification challenge. IEEE journal of biomedical and health informatics 22, 503–515.
  73. A collaborative resource to build consensus for automated left ventricular segmentation of cardiac mr images. Medical image analysis 18, 50–62.
  74. Benchmarking framework for myocardial tracking and deformation algorithms: An open access database. Medical image analysis 17, 632–648.
  75. Espirit—an eigenvalue approach to autocalibrating parallel mri: where sense meets grappa. Magnetic resonance in medicine 71, 990–1001.
  76. Attention is all you need, in: Advances in neural information processing systems, pp. 5998–6008.
  77. Recommendation for cardiac magnetic resonance imaging-based phenotypic study: imaging part. Phenomics 1, 151–170.
  78. Cmrxrecon: an open cardiac mri dataset for the competition of accelerated image reconstruction. arXiv preprint arXiv:2309.10836 .
  79. Dimension: dynamic mr imaging with both k-space and spatial prior knowledge obtained via multi-supervised network training. NMR in Biomedicine 35, e4131.
  80. The extreme cardiac mri analysis challenge under respiratory motion (cmrxmotion). arXiv preprint arXiv:2210.06385 .
  81. One-dimensional deep low-rank and sparse network for accelerated mri. IEEE Transactions on Medical Imaging 42, 79–90.
  82. Deep separable spatiotemporal learning for fast dynamic cardiac mri. arXiv preprint arXiv:2402.15939 .
  83. One for multiple: Physics-informed synthetic data boosts generalizable deep learning for fast mri reconstruction. arXiv preprint arXiv:2307.13220 .
  84. Measurement-conditioned denoising diffusion probabilistic model for under-sampled medical image reconstruction, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 655–664.
  85. A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging. Medical image analysis 67, 101832.
  86. Physics-driven synthetic data learning for biomedical magnetic resonance: The imaging physics-based data synthesis paradigm for artificial intelligence. IEEE Signal Processing Magazine 40, 129–140.
  87. Gated channel transformation for visual recognition, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 11794–11803.
  88. Direct: Deep image reconstruction toolkit. Journal of Open Source Software 7, 4278.
  89. vsharp: variable splitting half-quadratic admm algorithm for reconstruction of inverse-problems. arXiv preprint arXiv:2309.09954 .
  90. On retrospective k-space subsampling schemes for deep mri reconstruction. Magnetic Resonance Imaging .
  91. Recurrent variational network: A deep learning inverse problem solver applied to the task of accelerated mri reconstruction, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 732–741.
  92. Joint image reconstruction and sensitivity estimation in sense (jsense). Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine 57, 1196–1202.
  93. Restormer: Efficient transformer for high-resolution image restoration, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 5728–5739.
  94. fastmri: An open dataset and benchmarks for accelerated mri. arXiv preprint arXiv:1811.08839 .
  95. k-t clair: Self-consistency guided multi-prior learning for dynamic parallel mr image reconstruction, in: International Workshop on Statistical Atlases and Computational Models of the Heart, Springer. pp. 314–325.
  96. Camp-net: Consistency-aware multi-prior network for accelerated mri reconstruction. arXiv preprint arXiv:2306.11238 .
  97. Multi-site, multi-domain airway tree modeling. Medical Image Analysis 90, 102957.
  98. Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Medical image analysis 58, 101537.
  99. Cardiac segmentation on late gadolinium enhancement mri: a benchmark study from multi-sequence cardiac mr segmentation challenge. Medical Image Analysis 81, 102528.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (50)
  1. Jun Lyu (11 papers)
  2. Chen Qin (52 papers)
  3. Shuo Wang (382 papers)
  4. Fanwen Wang (20 papers)
  5. Yan Li (505 papers)
  6. Zi Wang (120 papers)
  7. Kunyuan Guo (6 papers)
  8. Cheng Ouyang (60 papers)
  9. Michael Tänzer (7 papers)
  10. Meng Liu (112 papers)
  11. Longyu Sun (4 papers)
  12. Mengting Sun (6 papers)
  13. Qin Li (179 papers)
  14. Zhang Shi (6 papers)
  15. Sha Hua (8 papers)
  16. Hao Li (803 papers)
  17. Zhensen Chen (3 papers)
  18. Zhenlin Zhang (8 papers)
  19. Bingyu Xin (8 papers)
  20. Dimitris N. Metaxas (84 papers)
Citations (10)
View on Semantic Scholar